L03 ggplot 2

Data Visualization (STAT 302)

Overview

The goal of this lab is to continue the process of unlocking the power of ggplot2 through constructing and experimenting with a few basic plots.

Datasets

We will be using the BRFSS survey which was introduced in the last lab. The data was supplied in cdc.txt file and should be in your /data subdirectory. If not, you need to download the last lab to get this data file. As a reminder, the dataset contains 20,000 complete observations/records of 9 variables/fields, described below.

• genhlth - How would you rate your general health? (excellent, very good, good, fair, poor)
• exerany - Have you exercised in the past month? (1 = yes, 0 = no)
• hlthplan - Do you have some form of health coverage? (1 = yes, 0 = no)
• smoke100 - Have you smoked at least 100 cigarettes in your life time? (1 = yes, 0 = no)
• height - height in inches
• weight - weight in pounds
• wtdesire - weight desired in pounds
• age - in years
• gender - m for males and f for females

# Load package(s)
library(tidyverse) 
# Load data
cdc <- read_delim('data/cdc.txt', delim = '|') |>
  mutate(
    genhlth = factor(
      genhlth, 
      levels = c('excellent', 'very good', 'good', 'fair', 'poor') 
    )
  )

Exercise 1

Using the cdc dataset, we want to look at the relationship between height and weight. Recreate the following graphics as precisely as possible.

Plot 1

Hints:

• Transparency is 0.2
• Minimal theme

Solution

#building plot 

ggplot(data = cdc, aes(x = height, y = weight, color = gender)) + 
  geom_point(aes(color = gender), alpha = 0.2) + 
  geom_smooth(se = FALSE, method = lm, fullrange = TRUE) + 
  xlab('Height (in)') + 
  ylab('Weight (lbs)') + 
  theme_minimal()

Plot 2

Hints:

• linewidth = 0.7

Solution

# building plot (contour/density plot)

ggplot(data = cdc, aes(x = height, y = weight)) + 
  geom_density_2d(aes(color = gender), linewidth = 0.7) + 
  xlab('Height (in)') + 
  ylab('Weight (lbs)') + 
  theme_minimal()

Plot 3

Hints:

• bins set to 35

Solution

# building plot (hexagonal)

ggplot(data = cdc, aes(x = height, y = weight)) + 
  geom_hex(bins = 35) + 
  xlab('Height (in)') + 
  ylab('Weight (lbs)') +
  theme_minimal() 

Plot 4

Hints:

• use a stat layer, not a geom layer
• geom = "polygon"

Solution

# building plot (hexagonal)

ggplot(data = cdc, aes(x = height, y = weight)) + 
  stat_density_2d(
    geom = 'polygon',
    mapping = aes(fill = after_stat(level)),
    show.legend = FALSE
  ) + 
  facet_wrap( ~ gender) + 
  xlab('Height (in)') + 
  ylab('Weight (lbs)') +
  theme_minimal() 

Exercise 2

Using the cdc_means dataset derived from the cdc dataset, recreate the following graphic as precisely as possible.

Hints:

• Hex color code #56B4E9
• 95% confidence intervals (1.96 or qnorm(0.975))
• Some useful values: 0.1, 0.7

# data wrangling
# calc mean and se for CI
cdc_means <- cdc |>
  mutate(wtloss = weight - wtdesire) |>
  group_by(genhlth) |>
  summarize(
    mean = mean(wtloss),
    se = sd(wtloss) / sqrt(n())
  ) |>
  mutate(genhlth = fct_reorder(factor(genhlth), desc(mean)))

Solution

# calculating bounds 

upper <- cdc_means$mean + qnorm(0.975) * cdc_means$se
lower <- cdc_means$mean - qnorm(0.975) * cdc_means$se

# building the plot

ggplot(cdc_means) + 
  geom_bar(aes(x = genhlth, y = mean), stat = 'identity', fill = '#56B4E9', width = 0.7) + 
  geom_errorbar(aes(x = genhlth, ymin = lower, ymax = upper), width = 0.1) + 
  xlab('General Health') + 
  ylab('Mean desired weight\nloss in lbs') + 
  theme_minimal()

Exercise 3

Using the cdc_weight_95ci dataset derived from the cdc dataset, recreate the following graphic as precisely as possible.

Hints:

• Useful values: 0.1, 0.5
• Need to know CI formula

# data wrangling
# calculate mean, se, and margin of error for CI formula
cdc_weight_95ci <- cdc |>
  group_by(genhlth, gender) |>
  summarise(
    mean_wt = mean(weight),
    se = sd(weight) / sqrt(n()),
    moe = qt(0.975, n() - 1) * se
  ) |> 
  ungroup()

Solution

# confidence interval

upper <- cdc_weight_95ci$mean_wt + cdc_weight_95ci$moe
lower <- cdc_weight_95ci$mean_wt - cdc_weight_95ci$moe

# building the plot, geom_pointrange()

ggplot(data = cdc_weight_95ci, aes(x = mean_wt, y = gender, color = genhlth, fill = gender)) + 
  geom_point(position = position_dodge(width = 0.5)) + 
  geom_errorbarh(aes(xmin = lower, xmax = upper), height = 0.1, position = position_dodge(width = 0.5)) + 
  xlab('Weight (lbs)') + 
  ylab('Gender') + 
  guides(fill = 'none', color = guide_legend(title = 'General Health\n(self reported)')) + 
  theme_minimal()